Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    closing HTML/XML tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ering
    0.48
    algebras
    0.48
    3
    0.46
    Rite
    0.45
     ALJ
    0.44
     ERK
    0.43
    ész
    0.43
    ">(
    0.43
     Iodine
    0.42
    ates
    0.42
    POSITIVE LOGITS
    。
    0.48
    >
    0.46
    最
    0.42
    uları
    0.40
    思います
    0.39
    >"
    0.39
    preco
    0.39
     微
    0.38
    ]-->
    0.38
    로
    0.38
    Act Density 0.027%

    No Known Activations